文章基本信息

标题：A Survey on Small Object Detection Based on Deep Learning
本地全文：下载
作者：Avarnita Chauhan ; Sapna Choudhary
期刊名称：International Journal of Advances in Engineering and Management
电子版ISSN：2395-5252
出版年度：2022
卷号：4
期号：2
页码：315-319
DOI：10.35629/5252-0402132135
语种：English
出版社：IJAEM JOURNAL
摘要：With the improving of the intelligent driving awareness, object detection as an important part of intelligent driving, has now become a research hotspot in the world. In recent years, convolutional neural network (CNN) has attracted more and more attention in the field of computer vision. CNN has made a series of important breakthroughs in the field of object detection. This paper introduces the object detection method based on deep learning. This paper mainly introduces the detection algorithm based on regional suggestion and regression, and analyses the advantages and disadvantages of the detection algorithm. Then, the disadvantages of these detection methods in detecting small objects and the difficulties in detecting small objects are analysed. On this basis, the public data sets and evaluation criteria related to small object detection are introduced.
关键词：Detection of moving objects;tracking of moving objects;behavior understanding;Neural Network;Caffe model;CNN